Sun Hui 孙辉
Research: AI for Data Compression (AI4Compression), High Performance Computing, and Time-Series LLMs.
Affiliated with Nankai-Baidu Joint Lab (NBJL).
News
2026.05
ACL 2026Two AI4Compression papers accepted at ACL 2026.
2026.02
CVPR 2026Learned image compression paper accepted at CVPR 2026.
2026.01
PreprintChatAD: LLM-driven time-series anomaly detection (work done at MSRA) posted on arXiv.
2025.10
Started research internship at Microsoft Research Asia (MSRA), focusing on Time-Series LLMs.
2025.07
KDD 2025PMKLC accepted at KDD 2025 (pp. 2725–2734).
CCF-ACCF-BCCF-C Conference rank
JCR Q1JCR Q2 Journal rank
EICSCDPreprint Other
First / Corresponding Author
16
ChatAD: Reasoning-Enhanced Time-Series Anomaly Detection with Multi-Turn Instruction Evolution
15
AgentGC: Evolutionary Learning-based Lossless Compression for Genomics Data with LLM-driven Multiple Agent
13
Learned Image Compression via Sparse Attention and Adaptive Frequency
12
PMKLC: Parallel Multi-Knowledge Learning-based Lossless Compression for Large-Scale Genomics Database
11
Genomics data lossless compression with (s,k)-mer encoding and deep neural networks
10
MSDZip: Universal Lossless Compression for Multi-source Data via Stepwise-parallel and Learning-based Prediction
9
Adaptive lossless compression for genomics data by multiple (s,k)-mer encoding and xLSTM
8
PQSDC: a parallel lossless compressor for quality scores data via sequences partition and run-length prediction mapping
7
A survey and benchmark evaluation for neural-network-based lossless universal compressors toward multi-source data
6
LRCB: A comprehensive benchmark evaluation of reference-free lossless compression tools for genomics sequencing long reads data
5
高错误率长序列基因组数据敏感序列识别并行算法
4
SR2C: A structurally redundant short reads collapser for optimizing DNA data compression
3
PMFFRC: a large-scale genomic short reads compression optimizer via memory modeling and redundant clustering
2
融合聚类和卷积神经网络的原理图美观度评价算法
1
融合过滤和相似度计算的高错误率基因组数据敏感序列识别
Co-authored
14
Efficient Learned Data Compression via Dual-Stream Feature Decoupling
5
Multi-source data lossless compression via parallel expansion mapping and xLSTM
4
ricME: long-read based mobile element variant detection using sequence realignment and identity calculation
3
Wireless energy: Paving the way for smart cities and a greener future
2
Eco-Energetical analysis of circular economy and community-based virtual power plants (CE-cVPP)
1
多维度评价科技工作责任主体信用模型与算法
Conference Talks
Invited Speaker
The Next Era of Medicine: AI-Driven Transformation
Serving as a peer reviewer for leading international conferences in AI, data mining, signal processing, and the web.
Conferences
AAAI CCF-A
AAAI Conference on Artificial Intelligence
202420252026
KDD CCF-A
ACM SIGKDD Conference on Knowledge Discovery and Data Mining
20252026
WWW CCF-A
The Web Conference
2025
ICASSP CCF-B
IEEE Int'l Conference on Acoustics, Speech and Signal Processing
2025
IJCNN CCF-C
International Joint Conference on Neural Networks
2025
Scholarships & Academic Awards
- 2024–25First Prize Doctoral Graduate Scholarship, Nankai University
- 2023–24Doctoral Graduate "GongNeng" Scholarship, Nankai University
- 2022–23Doctoral Graduate "GongNeng" Scholarship, Nankai University
- 2021–22Outstanding Graduate Student, Guangxi University
- 2021–22Annual Outstanding Student Scholarship, Guangxi University
- 2021–22First Prize Graduate Academic Scholarship, Guangxi University
- 2020–21First Prize Graduate Academic Scholarship, Guangxi University
- 2019–20Outstanding Graduate Cadre, Guangxi University
- 2017–18National Inspirational Scholarship of China
Competitions
2025
Computer Achievement Award, Guangxi Zhuang Autonomous Region Second Prize
2024
11th National Parallel Application Challenge, Team Leader National Second Prize · Top-2 in China
2024
Tianjin "Challenge Cup" Innovation and Entrepreneurship Plan, Technical Director Gold Prize · Top-1 in Tianjin
2024
Nankai University "President's Cup" Innovation and Entrepreneurship Competition, Technical Director First Prize
2023
"Huawei Cup" National College Student Storage Modeling Competition Second Prize · Top-2 in China
2020
8th National Parallel Application Challenge "Intel Cup" Parallel Fund Award · Top-9 in China
2020
Guangxi College Student Computer Design Competition Third Prize
2019
2019 Guangxi Computer Society Conference First Prize · Outstanding Paper
2017
"Data Creation Cup" National Mathematical Modeling Challenge First Prize
Patents
8
A Heuristic Layout and Routing Method for Circuit Schematic Diagrams
7
Method for Evaluating the Aesthetics Level of Circuit Layout, Routing, and Schematic Diagram
6
A Parallel Optimization Method for High-Throughput Genomics Sequencing Reads Data Compression
5
A Parallel Compression Method for High-Throughput Genomic Sequencing Quality Score Data
4
A Non-Intrusive Identification Method for Multi-Parameter Identification of Electromagnetic Equipment Based on Ensemble Algorithms
Software Copyrights
3
Research Integrity Evaluation Software System
2
DNA Sensitive Sequence Filtering Software
1
Improved RC4 Cryptography Auxiliary Teaching Platform